AI Article Synopsis
- - Machine learning models in chemistry depend on user-selected molecular descriptors to effectively predict active and inactive compounds, but privacy issues often limit data access, hindering model performance across a wider chemical range.
- - The proposed framework introduces re-trainable models that can easily transfer between local instances and reduce the need for extensive molecular descriptor selection.
- - By using Jupyter Notebooks for sharing models, this approach enables quick updates and broader chemical space evaluation while maintaining predefined parameters, which was tested with six different transporter datasets to confirm its effectiveness.
Article Abstract
Machine learning (ML) models require an extensive, user-driven selection of molecular descriptors in order to learn from chemical structures to predict actives and inactives with a high reliability. In addition, privacy concerns often restrict the access to sufficient data, leading to models with a narrow chemical space. Therefore, we propose a framework of re-trainable models that can be transferred from one local instance to another, and further allow a less extensive descriptor selection. The models are shared via a Jupyter Notebook, allowing the evaluation and implementation of a broader chemical space by keeping most of the tunable parameters pre-defined. This enables the models to be updated in a decentralized, facile, and fast manner. Herein, the method was evaluated with six transporter datasets (BCRP, BSEP, OATP1B1, OATP1B3, MRP3, P-gp), which revealed the general applicability of this approach.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9375336 | PMC |
| http://dx.doi.org/10.1186/s13321-022-00635-2 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!